27 September 2022 in IEEE Journal of Solid-State Circuits
Computing in-memory (CIM) is a promising new computing method to solve problems caused by von Neumann bottlenecks. It mitigates the need for transmitting large amounts of data between the processing and memory units, significantly decreasing the latency and energy consumption. However, writing back the calculation results for CIM can become a new bottleneck if only parallel computing is implemented. This study proposes a bidirectional static random access memory (SRAM) array structure comprising self-cycling eight-transistor (8T) cells, which can achieve full-array Boolean logic operations and read/write in two directions. The CIM results can be restored in in situ bit cells in a single cycle without additional memory. In addition, any data row can be copied into another row by controlling the intermediate transistor in the 8T cell. A 16-kb SRAM was implemented in the 28-nm CMOS technology to verify the effectiveness of the proposed design. The throughput of the proposed CIM macro is 1851.4 GOPS. Compared with the existing CIM macros, the throughput increased 3–56.6 times and the energy efficiency was as high as 270.5 TOPS/W at a supply voltage of 0.66 V. When the proposed circuits were applied to advanced encryption standard (AES) algorithms, the energy efficiency is increased by about 47.5%–63% compared to the von Neumann architecture.
21 February 2022 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Frequent to-and-from data transfers in the von Neumann architecture limit the overall throughput. One of the promising approaches used to overcome von Neumann bottleneck is in-memory computing (IMC) that aims to embed computing in memory to reduce the transfer of memory-processor data. This study proposes a configurable 6-transistor (6T) static random access memory (SRAM) array with a multilevel shared structure for IMC. A multilevel shared structure can effectively improve the utilization rate of the module. In addition to the conventional SRAM operation, the configurable structure can also perform the sum of absolute differences (SAD) and Hamming distance (HD) calculations. To quickly identify the minimum value among multiple calculation results, a four-input sense amplifier (SA) is proposed. The performance of the proposed memory is simulated in a 65-nm CMOS process. The post-layout simulation results show good linearity of the multirow read in the SAD and HD modes. The mean time required by the four-input SA to obtain the result is 190 ps. The SAD and HD calculations yield consumptions of 67.44 fJ/byte and 0.64 fJ/bit, respectively, at 0.8 V. Furthermore, a single column-sharing comparator consumes 2.78 and 3.41 pJ at 0.8 V in the SAD and HD modes, respectively.
10 May 2023 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
A possible approach to overcome the von Neumann bottleneck and meet the increasing demand for better computing performance is to computing in-memory (CIM). The results of the in-memory calculations are primarily reflected in the vertical bitline (BL) analog voltage. However, the nonlinearity of the BL discharge deteriorates with the increase in discharge voltage. In this study, we propose a diagonal symmetry weight block (DSWB) based on an eight-transistor (8T) static random access memory (SRAM) that can achieve multibit transposable operations. In addition, to guarantee linearity and complete multibit multiplication operations, we propose a cascode current mirror (CCM)-based multiplier. To achieve low-overhead and more efficient quantification, our proposed CIM macro uses a counter-type quantization circuit to read out the analog calculation results. We simulated the performance of the proposed 8T SRAM in a 28-nm complementary metal–oxide–semiconductor process. The integral nonlinearity (INL) of the proposed CCM-based CIM decreased by approximately 54.4% compared with the traditional CIM. Furthermore, the proposed in-memory multibit multiplication throughput density was 6.74 GOPS/kb; this throughput density improvement is approximately 3.3–10.5 times higher than the existing CIM works.
14 September 2022 in Microelectronics Journal
19 March 2024 in Microelectronics Journal
21 March 2025 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
In the realm of charge-domain computing-in-memory (CIM) macros, reducing the area of capacitor ladder and analog-to-digital converter (ADC) while maintaining high throughput remains a significant challenge. This brief introduces an adjustable-weight CIM macro designed to enhance both energy efficiency and area efficiency for convolutional neural networks (CNNs). The proposed architecture uses: 1) a customized 9T1C bit cell for sensing margin improvement and bidirectional decoupled read ports; 2) a hierarchical capacitance weighting (HCW) structure that achieves a weight accumulation of 1/2/4 bits with less capacitance area and weighting time; and 3) a two-step capacitive comparison ADCs (TC-ADCs) readout scheme to improve area efficiency and throughput. The proposed 8-kb static random address memory (SRAM) CIM macro is implemented using 28-nm CMOS technology. It can achieve an energy efficiency of 224.4 TOPS/W and an area efficiency of 21.894 TOPS/mm2, and the accuracies on MNIST, CIFAR-10, and CIFAR-100 datasets are 99.67%, 89.13%, and 67.58% with a 4-b input and 4-b weight.